Serverless Inference is a fully managed feature providing on-demand model-serving capability.
During the beta, Serverless Inference will be free to use. Any additional Akamai Cloud services used will be billed at the published rates.
- Discover fast and simple access to inferencing service
- Run open-weight models on Akamai Cloud
- Eliminate provisioning and managing GPU infrastructure
- Build latency-sensitive, real-time AI apps and agents